CN111599361A - Awakening method and device, computer storage medium and air conditioner - Google Patents
Awakening method and device, computer storage medium and air conditioner Download PDFInfo
- Publication number
- CN111599361A CN111599361A CN202010406233.7A CN202010406233A CN111599361A CN 111599361 A CN111599361 A CN 111599361A CN 202010406233 A CN202010406233 A CN 202010406233A CN 111599361 A CN111599361 A CN 111599361A
- Authority
- CN
- China
- Prior art keywords
- user
- mouth shape
- wake
- voice
- awakening
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000004590 computer program Methods 0.000 claims description 10
- 230000002618 waking effect Effects 0.000 claims description 5
- 230000006870 function Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000005236 sound signal Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention provides a wake-up method, which comprises the following steps: acquiring a voice awakening word, wherein the voice awakening word corresponds to a preset mouth shape; comparing the position of a sound source which sends out the voice awakening word with the position of a user, and comparing the mouth shape of the user with a preset mouth shape; when the position of the sound source matches the position of the user, and the user's mouth shape matches a predetermined mouth shape, a wake-up operation is performed. The method can preliminarily judge whether the awakening word is sent by the user or not by comparing the sound source position with the user position, and further confirm whether the awakening word is sent by the user or not by combining the mouth shape, so that the problem that the air conditioner is awakened by mistake due to mistake identification of the awakening word can be effectively avoided.
Description
Technical Field
The invention relates to the technical field of air conditioners, in particular to a wake-up method, a wake-up device, a computer storage medium and an air conditioner.
Background
The intelligent air conditioner generally has a voice control function, and a user can control the air conditioner to be turned on or off, adjust the operation mode, set the temperature, set the wind speed and the like by speaking. At present, air conditioners with voice control functions are all provided with a wake-up mechanism, voice can be recognized only after the air conditioners are waken up, and the design can prevent the situation of misoperation of users in the process of daily use of the air conditioners, such as sending out voice commands unintentionally when the air conditioners are used, and changing the mode of the air conditioners by mistake, turning on and off the air conditioners by mistake and the like. The awakening mechanism has the advantages that when the air conditioner is not required to be controlled by voice, the voice module of the air conditioner can be in a standby state, and standby power consumption is reduced.
In real life, there are situations where a speech module is awoken by mistake due to environmental disturbances, such as television sound disturbances. At present, the reduction of the awakening sensitivity is a solution, but the method cannot fundamentally solve the reason, so that not only can the condition of mistaken awakening still exist, but also the normal use of the user can be influenced, and the instruction sent by the user cannot be identified. The other solution is that the human body sensor detects the position of the human body to judge whether the awakening command is sent by the user, but when the position of the user is closer to the sound source interference position, the method cannot eliminate the interference sound source.
Disclosure of Invention
The invention mainly aims to provide a wake-up method and an air conditioner so as to reduce the situation that the voice control air conditioner is mistakenly awakened.
One aspect of the present invention provides a wake-up method, including: acquiring a voice awakening word, wherein the voice awakening word corresponds to a preset awakening mouth shape; comparing the position of a sound source which sends the voice awakening word with the position of a user, and comparing the mouth shape of the user with the preset awakening mouth shape; and when the position of the sound source is matched with the position of the user and the mouth shape of the user is matched with the preset awakening mouth shape, executing awakening operation.
Therefore, whether the awakening words are sent out from the direction of the user can be confirmed by comparing the sound source position with the user position, and whether the awakening words are sent out by the user is further confirmed by identifying the mouth shape of the user, so that mistaken awakening of the air conditioner is avoided.
Optionally, the obtaining a voice wakeup word includes: receiving a voice signal of a user, the voice signal being received by a microphone array; and detecting voice awakening words in the voice signals.
Therefore, the air conditioner can receive indoor sound signals in real time and obtain awakening words in time.
Optionally, the comparing the position of the sound source which utters the voice wakeup word with the position of the user includes: calculating the position of the sound source according to the time difference of the voice signal reaching each microphone in the microphone array; acquiring a user image; acquiring the position of the user according to the user image; and comparing the position of the sound source with the position of the user, and judging whether the position of the sound source is matched with the position of the user.
Therefore, the sound source position and the user position can be obtained, and whether the awakening word is possibly sent by the user or not can be judged.
Optionally, the obtaining the position of the user according to the user image includes: dividing a real space represented by the user image into a plurality of regions; identifying a region in which the user is located in the user image; and taking the position of the area where the user is located as the position of the user.
Therefore, the current position of the user can be obtained according to the user image.
Optionally, the comparing the position of the sound source which sends the voice awakening word with the position of the user, and comparing the mouth shape of the user with the preset awakening mouth shape comprises: comparing the position of the sound source which sends the voice awakening word with the position of a user; if the position of the sound source is not matched with the position of the user, not comparing the mouth shape of the user with the preset awakening mouth shape; and if the position of the sound source is matched with the position of the user, comparing the mouth shape of the user with the preset awakening mouth shape.
Therefore, when the sound source position is not matched with the user position, the awakening word can be judged not to be sent by the user, the mouth shape of the user is stopped being further identified, the calculation amount can be reduced, the waste of calculation resources and storage resources is prevented, when the sound source position is matched with the user position, whether the user sends the awakening word or not is confirmed by identifying the mouth shape of the user, and mistaken awakening of the air conditioner is prevented.
Optionally, the comparing the position of the sound source that sends the voice wake-up word with the position of the user, and comparing the mouth shape of the user with the preset wake-up mouth shape further includes: acquiring a user image; according to the user image, recognizing the mouth shape of the user in the user image; and comparing the mouth shape of the user with the preset awakening mouth shape, and judging whether the mouth shape of the user is matched with the preset awakening mouth shape.
Therefore, whether the awakening word is sent by the user or not can be confirmed according to the mouth shape.
Optionally, the wake action comprises sounding a wake feedback tone to the user.
Therefore, the air conditioner can be awakened to start working, and a user is reminded that the air conditioner is awakened.
In another aspect, the present invention further provides a wake-up apparatus, which is applied to the wake-up method according to any one of the first aspect, and includes: the device comprises a wake-up word acquisition module, a voice wake-up word acquisition module and a voice recognition module, wherein the wake-up word acquisition module is used for acquiring a voice wake-up word which corresponds to a preset wake-up mouth shape; the comparison module is used for comparing the position of a sound source sending the voice awakening word with the position of a user and comparing the mouth shape of the user with the preset awakening mouth shape; and the awakening module is used for executing awakening operation when the position of the sound source is matched with the position of the user and the mouth shape of the user is matched with the preset awakening mouth shape.
In another aspect, the present invention further provides a computer readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the wake-up method according to any one of the first aspect.
Another aspect of the present invention provides an air conditioner, comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the wake-up method according to any of the first aspect when executing the computer program.
The advantages of the air conditioner, the wake-up device and the computer readable storage medium are the same as those of the wake-up method, and are not described herein again.
Drawings
Fig. 1 schematically shows a flowchart of a wake-up method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating an embodiment of the present invention for obtaining a location of a user;
FIG. 3 is a schematic diagram of a microphone array receiving a speech signal according to an embodiment of the invention;
FIG. 4 is a flow chart schematically illustrating another wake-up method provided by an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a wake-up apparatus according to another embodiment of the present invention;
fig. 6 schematically shows a structural diagram of each module of an air conditioner according to another embodiment of the present invention.
Detailed Description
In order to make the purpose, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 schematically shows a flowchart of a wake-up method according to an embodiment of the present invention. In the present embodiment, an air conditioner is taken as an application scenario, and the wakeup method in the present embodiment is described in detail with reference to fig. 1 and fig. 2 to 6.
Referring to fig. 1, a wake-up method according to an embodiment of the present invention includes S110 to S130.
S110, acquiring a voice awakening word, wherein the voice awakening word corresponds to a preset awakening mouth shape.
In this embodiment, when the air conditioner is in a standby state, the sound in the environment where the air conditioner is located is monitored in real time, the user sends an instruction, the user needs to send a wakeup word to wake up the air conditioner first, and after the air conditioner is woken up, the air conditioner can receive other instructions for controlling the operation of the air conditioner by the user.
In this embodiment, after the air conditioner is powered on and initialized, the air conditioner enters a standby mode, and monitors a voice signal sent by a user in real time, before detecting a voice wakeup word, the user voice should be recognized first, and the voice wakeup word is detected from the user voice, including steps S101 to S102.
S101, receiving a voice signal of a user, wherein the voice signal is received by a microphone array.
In this embodiment, the air conditioner monitors all indoor sounds including video sounds, footstep sounds, conversation sounds among multiple users, indoor voices transmitted outdoors and the like, and after receiving the sounds, the air conditioner needs to extract the voices from the sounds as effective voice signals, so that external interference is reduced, and the probability of misrecognition is reduced.
It can be understood that the number of the microphones of the microphone array is more than 2, and the microphones can be arranged in a plurality of rows according to a word or not arranged according to a word.
S102, voice awakening words in the voice signals are detected.
In this embodiment, the voice wake-up word may exist in a plurality of sentence-type voice signals sent by the user, and the voice wake-up word may be extracted from the voice signals by using technical means such as natural language processing and voiceprint comparison, so as to accurately obtain the voice wake-up word.
It can be understood that the voice wake-up word may include various forms, for example, the voice wake-up word may include voice commands such as "hello", "power on", "start up", and the like, and may also be customized by the user.
S120, comparing the position of the sound source which sends the voice awakening word with the position of the user, and comparing the mouth shape of the user with the preset awakening mouth shape.
In this embodiment, if the user has sent the wake-up word, the position of the sound source is the same as the position of the user, and the mouth shape of the user should be the preset wake-up mouth shape, i.e., the position of the sound source and the position of the user are compared, and the mouth shape of the user and the preset wake-up mouth shape are compared, so that the mistaken recognition of the air conditioner caused by the mistaken recognition of other sounds as the wake-up word sent by the user can be prevented through the two comparisons.
Optionally, the position of the sound source is compared with the position of the user, and the mouth shape of the user is compared with a preset awakening mouth shape, and the two steps may be executed without being separated from each other.
In this embodiment, the position of the sound source is compared with the position of the user, and then the mouth shape of the user is compared with a preset awakening mouth shape, including S121 to S123.
And S121, comparing the position of the sound source which sends the voice awakening word with the position of the user.
In this embodiment, both the sound source position and the position of the user are sent to the controller of the air conditioner, so that the air conditioner determines whether the two positions are the same position to determine whether the voice wakeup word is sent by the user, and if the sound source position is the same as the position of the user, the wakeup word is sent from the direction in which the user is located, and the user may send the wakeup word. Specifically, S121 includes S1211 to S1214.
S1211, calculating a position of the sound source according to a time difference between arrival of the voice signal at each microphone of the microphone array.
Referring to fig. 3, in the present embodiment, a voice signal is received by a microphone array, and the sound source position is calculated according to a time difference of the voice signal reaching each microphone in the microphone array. As shown in fig. 3, the time and angle of arrival of the voice signal (straight arrow shown on the left side of the figure) at each microphone may be different due to different positions of each microphone, the waveform (wavy line shown on the right side of the figure) formed by the voice signal received by each microphone is different, and the sound source direction or the position of the sound source of the voice signal can be determined according to the combination of the time differences of the voice signal received by each microphone.
Optionally, the air conditioner may further obtain a specific position of the sound source by combining the time difference of the speech signal obtained by the microphone array according to the intensity of the speech signal.
And S1212, acquiring the user image.
In this embodiment, the user image is obtained through the camera, the user image refers to an image in a space where the air conditioner is currently located, and is used for recording user activities, the camera may be a dedicated camera configured for the air conditioner itself, or may be another camera used by the user daily, and the camera may perform data transmission with the air conditioner through a network.
S1213, according to the user image, the position of the user is obtained.
Referring to fig. 2, in this embodiment, the actual space represented by the user image is divided into a plurality of areas, the area where the user is located in the user image is identified, and the position of the area where the user is located is used as the position of the user. For example, as shown in fig. 2, the user image is divided into 8 regions, and through the algorithm analysis, the position of the user between the region 2 and the region 3 in the space can be determined, and further, according to the outline and the display size of the user in the image, the specific position of the user can be determined.
Optionally, after the camera acquires the user image, the camera uploads the user image to the server, the server executes a corresponding recognition algorithm to determine the user position, and then feeds the user position back to the camera, or the camera can directly perform local operation to obtain the user position. The server has large storage space and strong computing capability, and can quickly acquire the position of the user.
It can be understood that the image taken by the camera may be a video or a picture.
S1214, comparing the position of the sound source with the position of the user, and judging whether the position of the sound source is matched with the position of the user.
In the present embodiment, when the position of the sound source matches the position of the user, S123 is performed again, and when the position of the sound source does not match the position of the user, S122 is performed.
And S122, if the position of the sound source is not matched with the position of the user, not comparing the mouth shape of the user with the preset awakening mouth shape.
In this embodiment, if the position of the sound source is not matched with the position of the user, it is indicated that the wake-up word is not sent by the user, and actions such as identifying the mouth shape of the user, comparing the mouth shape of the user with a preset wake-up mouth shape, and the like are not performed, so that computing resources and storage resources of a controller and a camera of the air conditioner can be saved.
S123, if the position of the sound source is matched with the position of the user, comparing the mouth shape of the user with the preset awakening mouth shape.
In this embodiment, before comparing the user' S mouth shape with the awakening mouth shape, the method further includes S1231-1233.
And S1231, acquiring the user image.
In this embodiment, the user image and the image for identifying the user position are the same image.
S1231, according to the user image, recognizing the mouth shape of the user in the user image.
In this embodiment, after the camera captures the user image, the camera may transmit the image to the server, so that the server processes the user image to obtain data related to the mouth shape of the user in the image, such as the shape, size, and picture of the mouth shape. The server has large storage space and strong computing capability, and can quickly obtain the mouth shape related data of the user.
Optionally, after the camera captures the user image, the mouth shape of the user in the user image is locally recognized, and the related data of the mouth shape of the user is acquired.
S1231, comparing the mouth shape of the user with the preset awakening mouth shape, and judging whether the mouth shape of the user is matched with the preset awakening mouth shape.
In this embodiment, after acquiring the mouth shape data of the user, the data related to the mouth shape of the user is compared with the preset data of the waking mouth shape, for example, the similarity of the mouth shape data is calculated, the similarity of the mouth shape image is compared, and whether the mouth shape of the user is the waking mouth shape is determined.
It is understood that the preset mouth shape data is trained by a plurality of mouth shape data, the number of which is more than one.
Optionally, the preset die data is stored locally at the camera, on a server, or other storable medium.
S130, when the position of the sound source is matched with the position of the user, and the mouth shape of the user is matched with the preset awakening mouth shape, awakening operation is executed.
In this embodiment, when the position of the sound source is matched with the position of the user and the mouth shape of the user is matched with the preset awakening mouth shape, it is determined that the voice awakening word is sent by the user, and then an awakening operation is executed, so that the air conditioner corresponds to the next voice instruction of the user.
In this embodiment, the wake-up operation includes sending a wake-up feedback sound to the user to prompt the user that the air conditioner is woken up, and can receive other voice commands from the user.
In this embodiment, if the sound source position is the same as the position of the user, the mouth shape is not the wake-up mouth shape, which indicates that the wake-up word is sent from the direction where the user is located, but is not the instruction sent by the user to wake up the air conditioner, the wake-up operation is not executed, and false wake-up of the air conditioner is avoided.
Referring to fig. 4, fig. 4 schematically illustrates another implementation manner of the wake-up method provided by the embodiment of the present disclosure, including steps S410 to S450.
S410, acquiring a voice awakening word, wherein the voice awakening word corresponds to a preset awakening mouth shape;
and S420, acquiring the mouth shape of the user.
And S430, comparing the mouth shape of the user with the preset awakening mouth shape.
S440, if the mouth shape of the user is matched with the preset awakening mouth shape, acquiring the position of the sound source of the voice awakening word and the position of the user.
S450, comparing the position of the sound source of the voice awakening word with the position of the user.
S460, when the position of the sound source is matched with the position of the user, performing awakening operation.
In this embodiment, it is determined whether the mouth shape of the user is the mouth shape of the wake-up word, and it is determined whether the position of the user is the same as the position of the sound source that emits the wake-up word.
Referring to fig. 5, another embodiment of the invention provides a wake-up apparatus 500, which includes a wake-up word obtaining module 510, a comparing module 520, and a wake-up module 530, which are described in detail below. The device may perform the wake-up method as shown in fig. 1 and 4.
A wake-up word obtaining module 510, configured to obtain a voice wake-up word, where the voice wake-up word corresponds to a preset wake-up mouth shape;
a comparison module 520, configured to compare the position of the sound source that emits the voice wake-up word with the position of the user, and compare the mouth shape of the user with the preset wake-up mouth shape;
a wake-up module 530 configured to perform a wake-up operation when the position of the sound source matches the position of the user and the mouth shape of the user matches the preset wake-up mouth shape.
In this embodiment, when the wakeup word acquisition module 510 detects a voice wakeup word, the wakeup comparison module 520 acquires a position of a sound source that sends the voice wakeup word according to a time difference between arrival of a voice signal including the voice wakeup word at a microphone array, acquires a position of a user according to a user image captured by a camera, and compares the position of the sound source with the position of the user, when the position of the sound source matches the position of the user, the comparison module 520 acquires related data of a mouth shape of the user according to the user image, compares the data with preset wakeup word mouth shape data, and when the mouth shape data matches with the mouth shape data of a threshold, proves that the mouth shape data is a wakeup word mouth shape, the comparison module 520 sends a wakeup instruction to the wakeup module 530; the wake-up module 530 wakes up other operating modules of the air conditioner and sends a feedback tone to the user to prompt the user that the user can continue to issue instructions.
It is understood that the wakeup word acquiring module 510, the comparing module 520, and the wakeup module 530 may be combined and implemented in one module, or any one of the modules may be split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of the other modules and implemented in one module. According to an embodiment of the present invention, at least one of the wake word obtaining module 510, the comparing module 520, and the wake module 530 may be implemented at least in part as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented in hardware or firmware in any other reasonable manner of integrating or packaging a circuit, or in a suitable combination of three implementations of software, hardware, and firmware. Alternatively, at least one of the wake word obtaining module 510, the comparing module 520, and the wake module 530 may be at least partially implemented as a computer program module, which may perform the functions of the respective modules when the program is executed by a computer.
Another embodiment of the disclosure also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method of any of fig. 1.
Another embodiment of the present invention provides an air conditioner, a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein when the processor executes the computer program, the wake-up method as shown in any one of fig. 1 is implemented, so as to prevent a false wake-up situation occurring when the air conditioner is controlled by voice.
Referring to fig. 6, in the present embodiment, the air conditioner includes a microphone array 601, a voice module 602, a camera module 603, a control module 604, a broadcast module 605, and a load module 606. The microphone array 601 is used for receiving sound signals of the room where the air conditioner is located; the voice module 602 is configured to receive a voice signal transmitted by the microphone array 601, identify a voice signal in the voice signal, detect whether the voice signal includes a voice wakeup word, and acquire a position of a sound source; a camera module 603 for taking an image of the user and acquiring a position and a mouth shape of the user; the control module 604 is configured to compare whether the position of the user and the position of the sound source are the same, identify whether the mouth shape of the user is a wakeup word mouth shape, identify that the position of the user and the position of the sound source are the same, and control the responsible module 606 to operate and control the broadcast module 605 to broadcast a wakeup feedback tone when the mouth shape of the user is the wakeup word mouth shape; the broadcasting module 605 is configured to broadcast a wake-up feedback sound after it is confirmed that the user sends the wake-up word; and a load module 606 for heating or cooling.
Optionally, the voice module 602, the camera module 603, and the controller 604 may be divided into an offline operating mode and an online operating mode, for example, after the camera module 603 captures an image of a user, the image of the user may be locally analyzed to obtain a position and a mouth shape of the user, where the offline operating mode is an offline operating mode, and requires a chip with an arithmetic capability and a memory for storing the image of the user, and the method is faster in speed for obtaining the position and the mouth shape of the user, and is not limited by a network, but is still limited by a memory size (the larger the memory is, the more image templates and data can be stored for comparison, the higher the accuracy for identifying the position and the mouth shape of the user is), and the identification capability is limited; also can pass through the network with the user image and send the server to, make the server acquire user's position and mouth type according to the user image, this mode is online mode, need with camera and network connection, it possesses the communication ability to need the camera, because the storage space of server is bigger, the computing power is stronger, user position and mouth type that can be more accurate discernment, the chip computing power that makes the camera itself need not too strong, the memory need not too big, the hardware cost of having practiced thrift the air conditioner, but its operating efficiency can receive the network restriction.
It can be understood that the functions of acquiring the position of the user, the position of the sound source, the mouth shape of the user, comparing the positions of the user and the sound source, comparing the mouth shape of the user and the preset waking word mouth shape, and the like, which can be realized by the air conditioner, can be selectively divided into online and offline working modes according to the actual situation, that is, partial functions of the modules such as the voice module 602, the camera module 603, the controller 604, and the like, can be realized in the online mode, and partial functions are realized in the offline mode.
The advantages of the air conditioner provided in this embodiment are the same as the wake-up method provided in the above embodiment, and are not described herein again.
Although the present invention is disclosed above, the present invention is not limited thereto. Various changes and modifications may be effected therein by one skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (10)
1. A method of waking up, comprising:
acquiring a voice awakening word, wherein the voice awakening word corresponds to a preset awakening mouth shape;
comparing the position of a sound source which sends the voice awakening word with the position of a user, and comparing the mouth shape of the user with the preset awakening mouth shape;
and when the position of the sound source is matched with the position of the user and the mouth shape of the user is matched with the preset awakening mouth shape, executing awakening operation.
2. The method according to claim 1, wherein the obtaining the voice wake-up word comprises:
receiving a voice signal of a user, the voice signal being received by a microphone array;
and detecting voice awakening words in the voice signals.
3. The method according to claim 2, wherein comparing the position of the sound source that utters the voice wake-up word with the position of the user comprises:
calculating the position of the sound source according to the time difference of the voice signal reaching each microphone in the microphone array;
acquiring a user image;
acquiring the position of the user according to the user image;
and comparing the position of the sound source with the position of the user, and judging whether the position of the sound source is matched with the position of the user.
4. The wake-up method according to claim 3, wherein the obtaining the location of the user from the user image comprises:
dividing a real space represented by the user image into a plurality of regions;
identifying a region in which the user is located in the user image;
and taking the position of the area where the user is located as the position of the user.
5. The method according to claim 1, wherein comparing the position of the sound source that utters the voice wake-up word with the position of the user, and comparing the mouth shape of the user with the preset wake-up mouth shape comprises:
comparing the position of the sound source which sends the voice awakening word with the position of a user;
if the position of the sound source is not matched with the position of the user, not comparing the mouth shape of the user with the preset awakening mouth shape;
and if the position of the sound source is matched with the position of the user, comparing the mouth shape of the user with the preset awakening mouth shape.
6. The method for waking up as claimed in claim 1, wherein the comparing the position of the sound source emitting the voice wake-up word with the position of the user and the comparing the mouth shape of the user with the preset wake-up mouth shape further comprises:
acquiring a user image;
according to the user image, recognizing the mouth shape of the user in the user image;
and comparing the mouth shape of the user with the preset awakening mouth shape, and judging whether the mouth shape of the user is matched with the preset awakening mouth shape.
7. Wake-up method according to claim 1, characterized in that the wake-up operation comprises issuing a wake-up feedback tone to the user.
8. A wake-up device, for use in a wake-up method according to any one of claims 1 to 7, comprising:
the device comprises a wake-up word acquisition module, a voice wake-up word acquisition module and a voice recognition module, wherein the wake-up word acquisition module is used for acquiring a voice wake-up word which corresponds to a preset wake-up mouth shape;
the comparison module is used for comparing the position of a sound source sending the voice awakening word with the position of a user and comparing the mouth shape of the user with the preset awakening mouth shape;
and the awakening module is used for executing awakening operation when the position of the sound source is matched with the position of the user and the mouth shape of the user is matched with the preset awakening mouth shape.
9. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the wake-up method of any one of claims 1 to 7.
10. An air conditioner comprising: memory, processor and computer program stored on the memory and executable on the processor, characterized in that the processor implements the wake-up method according to any of claims 1 to 7 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010406233.7A CN111599361A (en) | 2020-05-14 | 2020-05-14 | Awakening method and device, computer storage medium and air conditioner |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010406233.7A CN111599361A (en) | 2020-05-14 | 2020-05-14 | Awakening method and device, computer storage medium and air conditioner |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111599361A true CN111599361A (en) | 2020-08-28 |
Family
ID=72192227
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010406233.7A Pending CN111599361A (en) | 2020-05-14 | 2020-05-14 | Awakening method and device, computer storage medium and air conditioner |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111599361A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112188341A (en) * | 2020-09-24 | 2021-01-05 | 江苏紫米电子技术有限公司 | Earphone awakening method and device, earphone and medium |
| CN112433770A (en) * | 2020-11-19 | 2021-03-02 | 北京华捷艾米科技有限公司 | Wake-up method and device for equipment, electronic equipment and computer storage medium |
| CN112634911A (en) * | 2020-12-21 | 2021-04-09 | 苏州思必驰信息科技有限公司 | Man-machine conversation method, electronic device and computer readable storage medium |
| CN112669837A (en) * | 2020-12-15 | 2021-04-16 | 北京百度网讯科技有限公司 | Awakening method and device of intelligent terminal and electronic equipment |
| CN113066488A (en) * | 2021-03-26 | 2021-07-02 | 深圳市欧瑞博科技股份有限公司 | Voice wake-up intelligent control method and device, electronic equipment and storage medium |
| CN113096656A (en) * | 2021-03-30 | 2021-07-09 | 深圳创维－Rgb电子有限公司 | Terminal device awakening method and device and computer device |
| CN113257251A (en) * | 2021-05-11 | 2021-08-13 | 深圳优地科技有限公司 | Robot user identification method, apparatus and storage medium |
| CN115223548A (en) * | 2021-06-29 | 2022-10-21 | 达闼机器人股份有限公司 | Voice interaction method, voice interaction device and storage medium |
| WO2024034980A1 (en) * | 2022-08-09 | 2024-02-15 | Samsung Electronics Co., Ltd. | Context-aware false trigger mitigation for automatic speech recognition (asr) systems or other systems |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104199545A (en) * | 2014-08-28 | 2014-12-10 | 青岛海信移动通信技术股份有限公司 | Method and device for executing preset operations based on mouth shapes |
| CN105096935A (en) * | 2014-05-06 | 2015-11-25 | 阿里巴巴集团控股有限公司 | Voice input method, device, and system |
| CN207440970U (en) * | 2017-08-29 | 2018-06-01 | 来邦科技股份公司 | A kind of alarm terminal based on Mouth-Shape Recognition |
| CN108154140A (en) * | 2018-01-22 | 2018-06-12 | 北京百度网讯科技有限公司 | Voice awakening method, device, equipment and computer-readable medium based on lip reading |
| CN110910878A (en) * | 2019-11-27 | 2020-03-24 | 珠海格力电器股份有限公司 | Voice wake-up control method and device, storage medium and household appliance |
| CN111145739A (en) * | 2019-12-12 | 2020-05-12 | 珠海格力电器股份有限公司 | Vision-based awakening-free voice recognition method, computer-readable storage medium and air conditioner |
-
2020
- 2020-05-14 CN CN202010406233.7A patent/CN111599361A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105096935A (en) * | 2014-05-06 | 2015-11-25 | 阿里巴巴集团控股有限公司 | Voice input method, device, and system |
| CN104199545A (en) * | 2014-08-28 | 2014-12-10 | 青岛海信移动通信技术股份有限公司 | Method and device for executing preset operations based on mouth shapes |
| CN207440970U (en) * | 2017-08-29 | 2018-06-01 | 来邦科技股份公司 | A kind of alarm terminal based on Mouth-Shape Recognition |
| CN108154140A (en) * | 2018-01-22 | 2018-06-12 | 北京百度网讯科技有限公司 | Voice awakening method, device, equipment and computer-readable medium based on lip reading |
| CN110910878A (en) * | 2019-11-27 | 2020-03-24 | 珠海格力电器股份有限公司 | Voice wake-up control method and device, storage medium and household appliance |
| CN111145739A (en) * | 2019-12-12 | 2020-05-12 | 珠海格力电器股份有限公司 | Vision-based awakening-free voice recognition method, computer-readable storage medium and air conditioner |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112188341A (en) * | 2020-09-24 | 2021-01-05 | 江苏紫米电子技术有限公司 | Earphone awakening method and device, earphone and medium |
| CN112188341B (en) * | 2020-09-24 | 2024-03-12 | 江苏紫米电子技术有限公司 | Earphone awakening method and device, earphone and medium |
| CN112433770A (en) * | 2020-11-19 | 2021-03-02 | 北京华捷艾米科技有限公司 | Wake-up method and device for equipment, electronic equipment and computer storage medium |
| CN112669837A (en) * | 2020-12-15 | 2021-04-16 | 北京百度网讯科技有限公司 | Awakening method and device of intelligent terminal and electronic equipment |
| CN112634911A (en) * | 2020-12-21 | 2021-04-09 | 苏州思必驰信息科技有限公司 | Man-machine conversation method, electronic device and computer readable storage medium |
| CN113066488B (en) * | 2021-03-26 | 2023-10-27 | 深圳市欧瑞博科技股份有限公司 | Voice wakeup intelligent control method and device, electronic equipment and storage medium |
| CN113066488A (en) * | 2021-03-26 | 2021-07-02 | 深圳市欧瑞博科技股份有限公司 | Voice wake-up intelligent control method and device, electronic equipment and storage medium |
| CN113096656A (en) * | 2021-03-30 | 2021-07-09 | 深圳创维－Rgb电子有限公司 | Terminal device awakening method and device and computer device |
| CN113257251A (en) * | 2021-05-11 | 2021-08-13 | 深圳优地科技有限公司 | Robot user identification method, apparatus and storage medium |
| CN113257251B (en) * | 2021-05-11 | 2024-05-24 | 深圳优地科技有限公司 | Robot user identification method, apparatus and storage medium |
| CN115223548A (en) * | 2021-06-29 | 2022-10-21 | 达闼机器人股份有限公司 | Voice interaction method, voice interaction device and storage medium |
| CN115223548B (en) * | 2021-06-29 | 2023-03-14 | 达闼机器人股份有限公司 | Voice interaction method, voice interaction device and storage medium |
| WO2024034980A1 (en) * | 2022-08-09 | 2024-02-15 | Samsung Electronics Co., Ltd. | Context-aware false trigger mitigation for automatic speech recognition (asr) systems or other systems |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111599361A (en) | Awakening method and device, computer storage medium and air conditioner | |
| CN108231079B (en) | Method, apparatus, device and computer-readable storage medium for controlling electronic device | |
| KR102335717B1 (en) | Voice control system and wake-up method thereof, wake-up device and home appliance, coprocessor | |
| CN111223497B (en) | Nearby wake-up method and device for terminal, computing equipment and storage medium | |
| CN107403621B (en) | Voice wake-up device and method | |
| JP4675840B2 (en) | Remote controller and home appliance | |
| US10991372B2 (en) | Method and apparatus for activating device in response to detecting change in user head feature, and computer readable storage medium | |
| CN107103906B (en) | Method for waking up intelligent device for voice recognition, intelligent device and medium | |
| WO2018169568A1 (en) | Query endpointing based on lip detection | |
| CN105575395A (en) | Voice wake-up method and apparatus, terminal, and processing method thereof | |
| CN111161714B (en) | Voice information processing method, electronic equipment and storage medium | |
| CN108806673B (en) | Intelligent device control method and device and intelligent device | |
| TW201403590A (en) | Signal processing apparatus and signal processing method | |
| CN109166575A (en) | Exchange method, device, smart machine and the storage medium of smart machine | |
| CN112130918A (en) | Intelligent device awakening method, device and system and intelligent device | |
| KR20190001067A (en) | Method and apparatus for speech recognition | |
| CN112233676A (en) | Intelligent device awakening method and device, electronic device and storage medium | |
| CN112420044A (en) | Voice recognition method, voice recognition device and electronic equipment | |
| CN113506568A (en) | Central control and intelligent equipment control method | |
| CN113160815A (en) | Intelligent control method, device and equipment for voice awakening and storage medium | |
| CN112272332B (en) | Awakening method and device of intelligent set top box, electronic equipment and storage medium | |
| CN116226701A (en) | Identification module, identification method and intelligent door lock | |
| CN112269322A (en) | Awakening method and device of intelligent device, electronic device and medium | |
| CN113905264A (en) | Voice control system based on voice remote controller | |
| CN112786044A (en) | Voice control method, device, main controller, robot and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200828 |
|
| RJ01 | Rejection of invention patent application after publication |